Recently updated channels

Pick one to see only that channelBrowse all channels →
Matthew Bermantoday +1Theo - t3․ggyesterday +74AI Engineeryesterday +2a16z2 days ago +1The Builders2 days ago +1硅谷1012 days ago +1SemiAnalysis2 days ago +1Chris Williamson2 days agoCheeky Pint2 days agoInvest Like The Best2 days ago

Results

1 articles
Sort
ChannelJane StreetTopicTransformers & attentionSpeakers2 people
7 slides1:16:29EN
Jane Street· Aug 26, 2026Grant Sanderson and Alok Puranik: Positional Encodings Through Group TheoryGrant Sanderson, Alok Puranik · 3Blue1BrownStarting with assumptions about attention, they derive matrix exponentials and connect rotations, decay and Jordan blocks to RoPE and ALiBi.Transformers & attentionMathematicsML fundamentals+1